© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47277
    Prev
    Next
    INDEX
    Explanations

    to + verb instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»ĻäºĨæĪij
    -0.07
    çŃīå¾ħçĿĢ
    -0.07
    åĩĨäºĪ
    -0.07
    æĻļ
    -0.06
    åı¯ä¾Ľ
    -0.06
    atively
    -0.06
    ula
    -0.06
    è¦ģåĬłå¤§
    -0.06
    æĭĽæīĭ
    -0.06
    æī¿æĭħçĿĢ
    -0.06
    POSITIVE LOGITS
    odel
    0.08
     Decompiled
    0.08
    /how
    0.08
    æ¶ħ
    0.08
    è§ģ她
    0.08
    nder
    0.07
    ä¸įè¨ĢèĢĮåĸ»
    0.07
    ×Ļ×Ļ×Ŀ
    0.07
    è§ģæѤ
    0.07
     isnt
    0.07
    Activations Density 0.255%

    No Known Activations